SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

As Large Language Models LLMs are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals...

Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications

Recent advancements in LLMs indicate potential for novel applications, e.g., through reasoning capabilities in the latest OpenAI and DeepSeek models. For applying these models in specific domains beyond text generation, LLM-based multi-agent approaches can be utilized that solve complex tasks by...

Theoretically Unmasking Inference Attacks against LDP-Protected Clients in Federated Vision Models

Federated Learning enables collaborative learning among clients via a coordinating server while avoiding direct data sharing, offering a perceived solution to preserve privacy. However, recent studies on Membership Inference Attacks MIAs have challenged this notion, showing high success rates...

CVE-2025-6030

Use of fixed learning codes, one code to lock the car and the other code to unlock it, in the Key Fob Transmitter in Cyclone Matrix TRF Smart Keyless Entry System, which allows a replay attack. Research was completed on the 2024 KIA Soluto. Attack confirmed on other KIA Models in Ecuador...

The Safety Reminder: a Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language Models

As Vision-Language Models VLMs demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models LLMs, VLMs face unique vulnerabilities due to their multimodal...

Step-By-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models

Whitepaper called Step-By-Step Reasoning Attack: Revealing 'Erased' Knowledge In Large Language Models...

CVE-2025-6030

Use of fixed learning codes, one code to lock the car and the other code to unlock it, in the Key Fob Transmitter in Cyclone Matrix TRF Smart Keyless Entry System, which allows a replay attack. Research was completed on the 2024 KIA Soluto. Attack confirmed on other KIA Models in Ecuador...

CVE-2025-6030 Autoeastern Smart Keyless Entry System Replay Attack

Use of fixed learning codes, one code to lock the car and the other code to unlock it, in the Key Fob Transmitter in Cyclone Matrix TRF Smart Keyless Entry System, which allows a replay attack. Research was completed on the 2024 KIA Soluto. Attack confirmed on other KIA Models in Ecuador...

CVE-2025-6030 Autoeastern Smart Keyless Entry System Replay Attack

Use of fixed learning codes, one code to lock the car and the other code to unlock it, in the Key Fob Transmitter in Cyclone Matrix TRF Smart Keyless Entry System, which allows a replay attack. Research was completed on the 2024 KIA Soluto. Attack confirmed on other KIA Models in Ecuador...

CVE-2025-6030

CVE-2025-6030 concerns the Cyclone Matrix TRF Smart Keyless Entry System’s Key Fob Transmitter, where the use of fixed learning codes enables a replay attack. The issue affects Cyclone Matrix TRF-based keyless systems and was demonstrated on a 2024 Kia Soluto, with reports of attacks on other Kia...

CVE-2025-45988

Blink routers BL-WR9000 V2.4.9 , BL-AC2100AZ3 V1.0.4, BL-X10AC8 v1.0.5 , BL-LTE300 v1.2.3, BL-F1200AT1 v1.0.0, BL-X26AC8 v1.2.8, BLAC450MAE4 v4.0.0 and BL-X26DA3 v1.2.7 were discovered to contain multiple command injection vulnerabilities via the cmd parameter in the bsSetCmd function...

CVE-2025-45985

Blink routers BL-WR9000 V2.4.9 , BL-AC2100AZ3 V1.0.4, BL-X10AC8 v1.0.5 , BL-LTE300 v1.2.3, BL-F1200AT1 v1.0.0, BL-X26AC8 v1.2.8, BLAC450MAE4 v4.0.0 and BL-X26DA3 v1.2.7 were discovered to contain a command injection vulnerability via the bsSetSSIDHide function...

CVE-2025-45984

Blink routers BL-WR9000 V2.4.9, BL-AC1900 V1.0.2, BL-AC2100AZ3 V1.0.4, BL-X10AC8 V1.0.5, BL-LTE300 V1.2.3, BL-F1200AT1 V1.0.0, BL-X26AC8 V1.2.8, BLAC450MAE4 V4.0.0 and BL-X26DA3 V1.2.7 were discovered to contain a command injection vulnerability via the routepwd parameter in the sub45B238 functio...

LB-LINK多款产品 安全漏洞

LB-LINK BL-X26 and others are products of China Bilink LB-LINK.LB-LINK BL-X26 is a wireless router.LB-LINK BL-LTE300 is a wireless router.LB-LINK BL-AC2100 is a wireless Wi-Fi 6 router. A security vulnerability exists in several LB-LINK products, which stems from a command injection in the cmd...

Towards Understanding the Cognitive Habits of Large Reasoning Models

Large Reasoning Models LRMs, which autonomously produce a reasoning Chain of Thought CoT before producing final responses, offer a promising approach to interpreting and monitoring model behaviors. Inspired by the observation that certain CoT patterns -- e.g., "Wait, did I miss anything?'' --...

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models

As Diffusion Models DM generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the single-domain of initial Gaussian noise for generation, which...

User Perceptions and Attitudes toward Untraceability in Messaging Platforms

Mainstream messaging platforms offer a variety of features designed to enhance user privacy, such as disappearing messages, password-protected chats, and end-to-end encryption E2EE, which primarily protect message contents. Beyond contents, the transmission of messages generates metadata that can...

SoK: Evaluating Jailbreak Guardrails for Large Language Models

Large Language Models LLMs have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety mechanisms. Guardrails--external defense mechanisms that monitor and control LLM interaction--have emerged as a promisi...

TimberStrike: Dataset Reconstruction Attack Revealing Privacy Leakage in Federated Tree-Based Systems

Federated Learning has emerged as a privacy-oriented alternative to centralized Machine Learning, enabling collaborative model training without direct data sharing. While extensively studied for neural networks, the security and privacy implications of tree-based models remain underexplored. This...

Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR

Extended reality XR systems, which consist of virtual reality VR, augmented reality AR, and mixed reality XR, offer a transformative interface for immersive, multi-modal, and embodied human-computer interaction. In this paper, we envision that multi-modal multi-task M3T federated foundation model...